Pai 的 AI 雷达

安全治理

今天：SoK（Agent 原型），Bridging Vision Foundation（arXiv:2609）。并行还有 What execs and。

日期
2026/09/15
今日条目
74
当前类目
3
往期2026/09/15
全部74编码代理4Agent与工具3个人助理1模型与评测27创作成片9开发与开源11产品接入19
领域硬件边缘1生信医疗6法律合规1金融1安全治理3行业观察15
#01

SoK: Rethinking Jailbreaking in the Era of Agentic AI: Attacks, Defenses, and Practical Consideration

arXiv:2609.12413v1 Announce Type: new Abstract: Large language models (LLMs) are rapidly evolving from conversational assistants into agentic AI systems that reason, plan, invoke tools, maintain persistent memory, communicate with other agents, and execute multi-step tasks. At th

推荐理由SoK: Rethinking Jailbreaking in the Era：arXiv:2609.12413v1 Announce Type: new Abstract: Large language models (LLMs) are。
模型与评测安全治理arXiv cs.AI 官方
arxiv.org打开原文
#02

Bridging Vision Foundation Model Priors with CLIP for Spatial-aware Few-shot Anomaly Detection in Medical Images

arXiv:2609.12454v1 Announce Type: cross Abstract: Vision-Language Models such as CLIP enable effective few-shot medical anomaly detection (AD) via strong image-text semantic alignment. However, their globally contrastive pretraining lacks explicit spatial supervision, limiting pr

推荐理由Bridging Vision Foundation Model Priors：arXiv:2609.12454v1 Announce Type: cross Abstract: Vision-Language Models such as CLIP。
模型与评测安全治理arXiv cs.AI 官方
arxiv.org打开原文
#03

What execs and politicians are saying about slowing down AI development

Dario Amodei kicked off a flood of statements over the past few days about AI safety by publishing a long essay titled "We Must Pace the Frontier" detailing why AI development should be slowed down. Other AI leaders and politicians are speaking out in favor of or opposing his poi

推荐理由What execs and politicians are saying：Dario Amodei kicked off a flood of statements over the past few days about AI safety。
产品接入安全治理The Verge AI
theverge.com打开原文